ai-augmentation-not-automation

ai-augmentation-not-automation is a skill for Claude Code from fatihguner/foreman. It costs 120 tokens per session (4,448 once invoked), scanned A, original, MIT.

A skill file about using AI to extend people’s abilities rather than replacing their work. The description does not provide further details about its guidance or tasks.

In plain words
What is it for?
AI-leadership work focused on augmentation rather than automation, based on the file name and path.
Why use it?
It may help frame AI use around human involvement, but the available description is too limited to identify specific advice.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the foreman plugin — 142 skills, 60 commands, 7 agents shipped together

Good fit AI-leadership work focused on augmentation rather than automation, based on the file name and path.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/fatihguner/foreman/ai-augmentation-not-automation
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add fatihguner/foreman --skill ai-augmentation-not-automation
Clone the repo
git clone --depth 1 https://github.com/fatihguner/foreman

Made for: Claude Code.

Or install foreman, the plugin that ships this one along with the rest of its 142 skills, 60 commands, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ai-augmentation-not-automation

README.md
[![agentmods](https://agentmods.dev/badge/skills/fatihguner/foreman/ai-augmentation-not-automation/github.svg)](https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation)
Your own site
<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-augmentation-not-automation/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ai-augmentation-not-automation

Your own site · 80×15
<a href="https://agentmods.dev/skills/fatihguner/foreman/ai-augmentation-not-automation"><img src="https://agentmods.dev/badge/skills/fatihguner/foreman/ai-augmentation-not-automation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 120 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,448 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00120 $0.04448
Opus 5 $0.00060 $0.02224
Sonnet 5 $0.00024 $0.00890
Haiku 4.5 $0.00012 $0.00445

Measured 5d ago against content hash e27827c4c172, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

ai-augmentation-not-automation scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/foreman/skills/ai-augmentation-not-automation/SKILL.md · 199 lines

How it starts

The opening of the file, as written. The whole thing — 199 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Read runtime and advisory rules before applying this skill. Other Foreman layers and the catalog are in ../../content/, relative to this SKILL.md.

AI Augmentation, Not Automation

In 2005, the online chess platform Playchess.com hosted a freestyle tournament with an unusual rule: any combination of humans and computers could enter. Grandmasters played alongside AI engines and hybrid teams of amateurs armed with laptops. The winners were not the grandmasters. They were not the strongest AI engines. They were two amateur players using three ordinary computers, who had developed a superior process for integrating human intuition with machine calculation. Garry Kasparov, observing the result, articulated the principle that would come to define a generation of human-AI research: "Weak human + machine + better process was superior to a strong computer alone and, remarkably, superior to a strong human + machine + inferior process." The centaur -- the mythological creature that is half human, half horse, greater than either -- had entered the business lexicon. The principle applies directly to every organisation contemplating AI: the goal is not to replace the human with the machine but to create a hybrid that outperforms both.


The Framework

The Automation Trap

Up to 60 percent of work activities could be automated, and this trend shows no signs of decelerating. Organisations pursue standardisation, streamlining, and speed. From a short-term financial perspective, automation is compelling: lower labour costs, consistent output, no sick days, no salary negotiations. One executive remarked with evident satisfaction that AI was "an absolute cost killer" for his clients.

The satisfaction is premature. Automation delivers short-term performance gains that mask four structural pathologies, each of which erodes the long-term capability of the organisation.

Pathology 1: Job fragmentation and polarisation. When AI automates the routine middle of the job spectrum -- administrative, bureaucratic, process-driven work -- the result is not a smaller, more skilled workforce. It is a bifurcated one. High-paid creative and strategic roles remain. Low-paid manual roles that are too expensive to automate remain. The middle disappears. Workers displaced from mid-level positions cannot immediately upskill to strategic roles; they fall into lower-paid work. Bargaining power erodes. Inequality increases. The socioeconomic instability that results does not stay outside the company gates -- it becomes the company's operating environment.

Read the full file on GitHub · 199 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago Changed · +198 lines · +120 tokens per session e27827c4c172
  2. 11d ago First seen · 1 lines · 0 tokens per session scan A 97e0b5d065ae

Subscribe to this mod's changes

ai-augmentation-not-automation is a skill published in the GitHub repository fatihguner/foreman (50 stars, last pushed 6d ago), licensed MIT. It adds 120 tokens to every session and 4,448 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.